These are the final papers.
| Date | Class | Meta-Topic | Topic | Presenters | Paper 1 | Paper 2 | Presentation
Review Panels | Things Due |
| Aug 31 2020 | 0 | Getting Situated | Intro | fouhey | | | | |
| Sep 2 2020 | 1 | | Reading, Writing,
& Arithmetic | fouhey | None | None | | |
| Sep 7 2020 | 2 | The Basics | Labor Day | | | | | |
| Sep 9 2020 | 3 | | Architectures | fouhey, fouhey, fouhey | Densely connected convolutional
networks (Huang et al. CVPR 2017) | Designing Network Design Spaces
(Radosavovic et al. CVPR 2020) | A; F | |
| Sep 14 2020 | 4 | Different Means
of Learning | Optimization | eslubana, fouhey, fouhey | Decoupled Weight Decay
Regularization (Loshchilov et al.
ICLR 2019) | On Empirical Comparisons of
Optimizers for Deep Learning (Choi
et al. Arxiv 2019) | B; G | |
| Sep 16 2020 | 5 | | Self-supervised learning | ckonicki, yushuz, yianz | Momentum Contrast for
Unsupervised Visual
Representation Learning (He et al.
2019) | Unsupervised Learning of Visual
Features by Contrasting Cluster
Assignments (Caron et al. Arxiv
2020) | C; H | |
| Sep 21 2020 | 6 | | Metalearning | fouhey, jiezzliu, shensq | Model-Agnostic Meta-Learning for
Fast Adaptation of Deep Networks
(Finn et al. ICML 2017) | Rethinking Few-Shot Image
Classification: A Good Embedding
Is All You Need? (Tian et al. ECCV
2020) | D; I | |
| Sep 23 2020 | 7 | Detection | Detection | hsuanc, kennyfan, robintzg | MaskRCNN (He et al. ICCV 2017) | PointRend: Image Segmentation as
Rendering (Kirillov et al. CVPR
2020) | E; J | |
| Sep 28 2020 | 8 | | More Detection | joecc, daynauth, guorui | LVIS: A Dataset for Large
Vocabulary Instance Segmentation
(Gupta et al. CVPR 2019) | Objects as Points (Zhou et al. Arxiv
2019) | F; A | |
| Sep 30 2020 | 9 | Data Gone Wrong | Dataset bias | dywsjtu, jminlee, tonyztc | An Unbiased Look at Dataset Bias
(Torralba and Efros CVPR 2011) | Do ImageNet Classifiers
Generalize to ImageNet? (Recht et
al. ICML 2019) | G; B | Re-Proposal Due |
| Oct 5 2020 | 10 | | Domain adaptation | fouhey, chengjia, hzwang | Understanding Self-Training for
Gradual Domain Adaptation (Kumar
et al. ICML 2020) | Cluster Alignment with a Teacher
for Unsupervised Domain
Adaptation (Deng et al. ICCV 2019) | H; C | |
| Oct 7 2020 | 11 | 3D | 3D – Implicit Functions | manasjb, kamako, dasyed | PIFu: Pixel-Aligned Implicit
Function for High-Resolution
Clothed Human Digitization (Saito
et al. ICCV 2019) | Occupancy Networks: Learning 3D
Reconstruction in Function Space
(Mescheder et al. CVPR 2019) | I; D | |
| Oct 12 2020 | 12 | | 3D – Multiview | fouhey, mingshuo, zyq | NeRF (Mildenhall et al. ECCV 2020) | Differentiable Volumetric
Rendering: Learning Implicit 3D
Representations without 3D
Supervision (Niemeyer et al. CVPR
2020) | J; E | |
| Oct 14 2020 | 13 | Embodiment | Navigation | bijustin, aliangdw, liubryan | Neural Topological SLAM for Visual
Navigation (Chaplot et al. CVPR
2020) | SoundSpaces: Audio-Visual
Navigation in 3D Environments
(Chen et al. ECCV 2020) | A; F | |
| Oct 19 2020 | 14 | | Robotics & Grasping | fouhey, spradeep, mwilmes | Grasping in the Wild: Learning 6DoF
Closed-Loop Grasping from
Low-Cost Demonstrations (Song et
al. RAL 2020) | 6-DOF Grasping for Target-driven
Object Manipulation in Clutter
(ICRA 2020) | B; G | Project Proposal Due |
| Oct 21 2020 | 15 | People | People | fouhey, fouhey, aligol | Learning joint reconstruction of
hands and manipulated objects
(Hasson et al. CVPR 2019) | Perceiving 3D Human-Object
Spatial Arrangements from a Single
Image in the Wild (Zhang et al. ECCV
2020) | C; H | |
| Oct 26 2020 | 16 | | Affordances | fouhey, stanlew, shiyuliu | Category-Level Articulated
Object Pose Estimation (Li et al.
CVPR 2020) | Grasping Field: Learning Implicit
Representations for Human Grasps
(Karunratanakul et al. Arxiv 2020) | D; I | |
| Oct 28 2020 | 17 | What Are Our
Models Doing? | Ethics & Fairness | fouhey, fouhey, sjabbour | Gender Shades: Intersectional
Accuracy Disparities in
Commercial Gender Classification
(Buolamwini and Gebru FAT 2018) | Dissecting racial bias in an
algorithm used to manage the health
of populations (Obermeyer et al.
Science 2019) | E; J | |
| Nov 2 2020 | 18 | | Interpretation | fouhey, fouhey, fouhey | Adversarial Filters of Dataset
Biases (Le Bras et al. ICML 2020) | Grounding Visual Explanations
(Hendricks et al. ECCV 2018) | F; A | |
| Nov 4 2020 | 19 | Time | Videos | ttzhan, zxbian, yuanfenw | Rescaling Egocentric Vision
(Damen et al. ECCV 2020) | What Matters in Unsupervised
Optical Flow (Jonschkowski et al.
ECCV 2020) | G; B | |
| Nov 9 2020 | 20 | | Reasoning about Time | fouhey, zycui, zheyw | VisualCOMET: Reasoning about the
Dynamic Context of a Still Image
(Park et al. ECCV 2020) | Time-Agnostic Prediction:
Predicting Predictable Video
Frames (Jayaraman et al. ICLR 2019) | H; C | |
| Nov 11 2020 | 21 | Other Modalities | Language | muchen, shansal, tozhou | End-to-End Learning of Visual
Representations from Uncurated
Instructional Videos (Miech et al.
CVPR 2020) | Speech2Action: Cross-modal
Supervision for Action
Recognition (Nagrani et al. CVPR
2020) | I; D | |
| Nov 16 2020 | 22 | | Sounds | fouhey, ninglu, jingzhuu | Self-Supervised Learning of
Audio-Visual Objects from Video
(Afouras et al. ECCV 2020) | VisualEchoes: Spatial Image
Representation Learning through
Echolocation (Gao et al. ECCV 2020) | J; E | |
| Nov 18 2020 | 23 | More Interesting
Achitectures | Graph Networks | baldeeb, dgeng, lhuo | SuperGlue: Learning Feature
Matching with Graph Neural
Networks (Sarlin et al. CVPR 2020) | Space-Time Correspondence as a
Contrastive Random Walk (Jabri et
al. Arxiv 2020) | A; F | Project Preliminary Report Due |
| Nov 23 2020 | 24 | | Thanksgiving | | | | | |
| Nov 25 2020 | 25 | Thanksgiving | Thanksgiving | | | | | |
| Nov 30 2020 | 26 | | Transformers | fouhey, johnmaxh, dengcy | Attention Is All You Need (Vaswani
et al. NeurIPS 2017) | Language Models are Few-Shot
Learners (Brown et al. Arxiv 2020) | B; G | |
| Dec 2 2020 | 27 | Generating Pictures | Generative Models | guanhuaw, wangyfan, mingyuy | Normalizing Flows: An
Introduction and Review of Current
Methods (Kobyzev et al. TPAMI 2020) | Generating Diverse High-Fidelity
Images with VQ-VAE-2 (Razavi et al.
NeurIPS 2019) | C; H | |
| Dec 7 2020 | 28 | | Graphics | fouhey, pkchen, hxwu | SynSin: End-to-end View Synthesis
from a Single Image (Wiles et al.
CVPR 2020) | Generative Pretraining from
Pixels (Chen et al. ICML 2020) | D; I | Project Final Report Draft
|