|
3 | 3 | ### Semantic Segmentation |
4 | 4 |
|
5 | 5 | | Paper | Notes | Author | Summary | |
6 | | -|-:-:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-:-:----------------------------------------------|-:-:-------------------------------------|-:-:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 6 | +|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------:|:---------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
7 | 7 | | [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://openaccess.thecvf.com/content_CVPR_2020/papers/Ouali_Semi-Supervised_Semantic_Segmentation_With_Cross-Consistency_Training_CVPR_2020_paper.pdf) (CVPR '20) | [HackMD](https://hackmd.io/@akshayk07/B1uYpeMNw) | [Akshay](https://akshayk07.weebly.com/) | This paper proposes cross-consistency training, where an invariance of the predictions is enforced over different perturbations applied to the outputs of the encoder (in a shared encoder and multiple decoder architecture). | |
8 | 8 | | [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](http://openaccess.thecvf.com/content_ICCV_2019/html/Takikawa_Gated-SCNN_Gated_Shape_CNNs_for_Semantic_Segmentation_ICCV_2019_paper.html) (ICCV '19) | [HackMD](https://hackmd.io/@akshayk07/ryhzTGJor) | [Akshay](https://akshayk07.weebly.com/) | This paper presents a 2-stream CNN i.e. one stream is normal CNN (classical stream) while the other is a shape stream, which explicitly processes shape information in a separate stream. | |
9 | 9 | | [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://arxiv.org/abs/1606.02147) | [HackMD](https://hackmd.io/@akshayk07/rJ4NL3sTB) | [Akshay](https://akshayk07.weebly.com/) | This paper presents a network architecture which is faster and more compact, for low real-time inference times. | |
|
14 | 14 | ### Domain Adaptation |
15 | 15 |
|
16 | 16 | | Paper | Notes | Author | Summary | |
17 | | -|-:-:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-:-:------------------------------------------------|-:-:-------------------------------------|-:-:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 17 | +|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------:|:---------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
18 | 18 | | [Domain Adaptive Semantic Segmentation Using Weak Labels](https://arxiv.org/abs/2007.15176) (ECCV '20) | [HackMD](https://hackmd.io/@akshayk07/rydQyAVHv) | [Akshay](https://akshayk07.weebly.com/) | This paper proposes a framework for Domain Adaptation (DA) in semantic segmentation with image-level weak labels in the target domain. They use weak labels to enable the interplay between feature alignment and pseudo-labeling, improving both in DA. | |
19 | 19 | | [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://arxiv.org/abs/2007.08702) | [HackMD](https://hackmd.io/@akshayk07/ByhfvJ7XP) | [Akshay](https://akshayk07.weebly.com/) | This paper proposes Domain Adaptation via Cross-domain Mixed Sampling which mixes images from two domains along with their corresponding labels. These mixed samples are trained on, along with the labelled data itself. | |
20 | 20 | | [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://openaccess.thecvf.com/content_CVPR_2020/html/Kim_Learning_Texture_Invariant_Representation_for_Domain_Adaptation_of_Semantic_Segmentation_CVPR_2020_paper.html) (CVPR '20) | [HackMD](https://hackmd.io/@akshayk07/B167fmyGD) | [Akshay](https://akshayk07.weebly.com/) | This paper uses style transfer to enforce texture invariance in the model, followed by self training to adapt to the target domain texture for the semantic segmentation task. | |
|
27 | 27 | ### Knowledge Distillation |
28 | 28 |
|
29 | 29 | | Paper | Notes | Author | Summary | |
30 | | -|-:-:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-:-:------------------------------------------------|-:-:-------------------------------------|-:-:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 30 | +|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------:|:---------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
31 | 31 | | [Distilling the Knowledge in a Neural Network](https://arxiv.org/pdf/1503.02531.pdf) (NIPS '14W) | [HackMD](https://hackmd.io/AntG2tWLQw-dflF5Y1fXig) | [Raj](https://github.com/RajGhugare19) | This paper is the first DL approach to transfer knowledge from a teacher network to a student network, and uses softened outputs of the teacher network for training the student network. | |
32 | 32 | | [A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning](http://openaccess.thecvf.com/content_cvpr_2017/papers/Yim_A_Gift_From_CVPR_2017_paper.pdf) (CVPR '17) | [HackMD](https://hackmd.io/@akshayk07/rkj6RFc28) | [Akshay](https://akshayk07.weebly.com/) | This paper formulates the knowledge to be transferred in terms of flow between layers, calculates it as the inner product between feature maps from 2 layers, and uses this for Knowledge Distillation. | |
33 | 33 | | [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://arxiv.org/abs/1612.03928) (ICLR '17) | [HackMD](https://hackmd.io/@akshayk07/BkzGciz38) | [Akshay](https://akshayk07.weebly.com/) | This paper defines attention for CNNs, and uses it to improve the performance of a student CNN network by forcing it to mimic the attention maps of a powerful teacher network. | |
|
37 | 37 | ### Active Learning |
38 | 38 |
|
39 | 39 | | Paper | Notes | Author | Summary | |
40 | | -|-:-:------------------------------------------------------------------------------------|-:-:------------------------------------------------|-:-:-------------------------------------|-:-:--------------------------------------------------------------------------------------------------------------------------------------------------| |
| 40 | +|:--------------------------------------------------------------------------------------:|:--------------------------------------------------:|:---------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------:| |
41 | 41 | | [Variational Adversarial Active Learning](https://arxiv.org/abs/1904.00370) (ICCV '19) | [HackMD](https://hackmd.io/CxZNGh6dS3m2axmP50iN8g) | [Akshay](https://akshayk07.weebly.com/) | This paper introduces a pool-based active learning strategy which learns a low dimensional latent space from labeled and unlabeled data using a VAE. | |
42 | 42 |
|
43 | 43 | ### Feature Detection and Description |
44 | 44 |
|
45 | 45 | | Paper | Notes | Author | Summary | |
46 | | -|-:-:---------------------------------------------------------------------------------------------------------------------------|-:-:----------------------------------------------------|-:-:------------------------------------------------------------------------------------|-:-:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 46 | +|:-----------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------:|:--------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
47 | 47 | | [D2 Net - A Trainable CNN for Joint Description and Detection of Local Features](https://arxiv.org/abs/1905.03561) (CVPR '19) | [HackMD](https://hackmd.io/@AniketGujarathi/SywvV8iQD) | [Aniket Gujarathi](https://www.linkedin.com/in/aniket-gujarathi/?originalSubdomain=in) | This paper introduces a Deep Learning based approach to solve the problem of local features detection and description using the detect-and-describe approach instead of the traditionally used detect-then-describe approach. | |
48 | 48 |
|
49 | 49 | ### Self Supervised Learning |
50 | 50 |
|
51 | 51 | | Paper | Notes | Author | Summary | |
52 | | -|-:-:---------------------------------------------------------------------------------------------------------------------------------|-:-:-----------------------------------------------------------|-:-:------------------------------------------------------------------------------------------------------------------------|-:-:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 52 | +|:-----------------------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
53 | 53 | | [Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection](https://arxiv.org/pdf/1902.01275.pdf) (ECCV '18) | [HackMD](https://hackmd.io/@6GX-kbOaSt6hNkpWQyj20A/r1tnl1gQD) | [Aayush](https://github.com/aayush-fadia), [Jayesh](https://github.com/jayeshk7), [Saketh](https://github.com/sakethbachu) | This paper presents a real-time RGB-based pipeline for object detection and 6D pose estimation, based on a variant of denoising autoencoder, which is an augmented encoder trained on views of a 3D model using domain randomization. | |
0 commit comments