Trending Research

Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet

6 May 2021lukemelas/do-you-even-need-attention

These results indicate that aspects of vision transformers other than attention, such as the patch embedding, may be more responsible for their strong performance than previously thought.

IMAGE CLASSIFICATION

203
6.06 stars / hour

Emerging Properties in Self-Supervised Vision Transformers

29 Apr 2021facebookresearch/dino

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).

COPY DETECTION SELF-SUPERVISED IMAGE CLASSIFICATION SELF-SUPERVISED LEARNING SEMANTIC SEGMENTATION VIDEO OBJECT DETECTION

1,728
3.57 stars / hour

Adversarial Open Domain Adaption for Sketch-to-Photo Synthesis

12 Apr 2021Mukosame/Anime2Sketch

In this paper, we explore the open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data.

DOMAIN ADAPTATION

430
2.46 stars / hour

Universal Language Model Fine-tuning for Text Classification

ACL 2018 mrdbourke/tensorflow-deep-learning

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.

CLASSIFICATION LANGUAGE MODELLING SENTIMENT ANALYSIS TEXT CLASSIFICATION TRANSFER LEARNING

851
1.73 stars / hour

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

5 May 2021DingXiaoH/RepMLP

We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers.

FACE RECOGNITION IMAGE CLASSIFICATION SEMANTIC SEGMENTATION

43
1.19 stars / hour

StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing

30 Apr 2021naver-ai/StyleMapGAN

Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.

IMAGE INTERPOLATION IMAGE MANIPULATION

162
1.13 stars / hour

ISTR: End-to-End Instance Segmentation with Transformers

3 May 2021hujiecpp/ISTR

However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

78
0.93 stars / hour

4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface

5 May 2021rabbityl/DeformingThings4D

Tracking non-rigidly deforming scenes using range sensors has numerous applications including computer vision, AR/VR, and robotics.

MOTION ESTIMATION

27
0.73 stars / hour

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

28 Apr 2021facebookresearch/suncet

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS).

IMAGE CLASSIFICATION

229
0.71 stars / hour

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

ICLR 2021 google-research/vision_transformer

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.

 Ranked #1 on Fine-Grained Image Classification on Oxford-IIIT Pets (using extra training data)

DOCUMENT IMAGE CLASSIFICATION FINE-GRAINED IMAGE CLASSIFICATION

2,417
0.48 stars / hour