Non-salient region object mining for weakly supervised semantic segmentation
Semantic segmentation aims to classify every pixel of an input image. Considering the
difficulty of acquiring dense labels, researchers have recently been resorting to weak labels …
difficulty of acquiring dense labels, researchers have recently been resorting to weak labels …
Jo-src: A contrastive approach for combating noisy labels
Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels
usually results in inferior model performance. Existing state-of-the-art methods primarily …
usually results in inferior model performance. Existing state-of-the-art methods primarily …
Hierarchical feature alignment network for unsupervised video object segmentation
Optical flow is an easily conceived and precious cue for advancing unsupervised video
object segmentation (UVOS). Most of the previous methods directly extract and fuse the …
object segmentation (UVOS). Most of the previous methods directly extract and fuse the …
Region graph embedding network for zero-shot learning
Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from
global features or image parts (regions) to the semantic space, which, however, fail to …
global features or image parts (regions) to the semantic space, which, however, fail to …
Pnp: Robust learning from noisy labels by probabilistic noise prediction
Label noise has been a practical challenge in deep learning due to the strong capability of
deep neural networks in fitting all training data. Prior literature primarily resorts to sample …
deep neural networks in fitting all training data. Prior literature primarily resorts to sample …
Fecanet: Boosting few-shot semantic segmentation with feature-enhanced context-aware network
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel
class in the query image with only a few annotated support images. The current correlation …
class in the query image with only a few annotated support images. The current correlation …
REVISE: A tool for measuring and mitigating bias in visual datasets
Abstract Machine learning models are known to perpetuate and even amplify the biases
present in the data. However, these data biases frequently do not become apparent until …
present in the data. However, these data biases frequently do not become apparent until …
Webly supervised fine-grained recognition: Benchmark datasets and an approach
Learning from the web can ease the extreme dependence of deep learning on large-scale
manually labeled datasets. Especially for fine-grained recognition, which targets at …
manually labeled datasets. Especially for fine-grained recognition, which targets at …
Hierarchical co-attention propagation network for zero-shot video object segmentation
Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a
video sequence without prior knowledge of these objects. However, existing ZS-VOS …
video sequence without prior knowledge of these objects. However, existing ZS-VOS …
Web-supervised network with softly update-drop training for fine-grained visual classification
Labeling objects at the subordinate level typically requires expert knowledge, which is not
always available from a random annotator. Accordingly, learning directly from web images …
always available from a random annotator. Accordingly, learning directly from web images …