ADE20K
PulseAugur coverage of ADE20K — every cluster mentioning ADE20K across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
Vision Transformers improved with selective token interaction
Researchers have identified a phenomenon called "semantic diffusion" that degrades the performance of Vision Transformers (ViTs) in dense prediction tasks over time. This occurs when global semantic information spreads …
-
Vision models ditch activations for polynomial alternatives
Researchers have developed new activation-free backbone architectures for vision models, utilizing polynomial functions instead of traditional pointwise nonlinearities like ReLU or GELU. These novel modules, integrated …
-
New TsallisPGD attack method improves adversarial attacks on semantic segmentation models
Researchers have developed TsallisPGD, a novel adversarial attack method designed to more effectively target semantic segmentation models. This new approach utilizes Tsallis cross-entropy, a generalized form of standard…
-
AdaVFM framework uses LLMs to adapt vision models for edge devices
Researchers have developed AdaVFM, a novel framework designed to make large vision foundation models more efficient for edge devices. This system dynamically adjusts computational load based on the complexity of the sce…
-
FractalMamba++ scales vision models across resolutions using Hilbert curves
Researchers have introduced FractalMamba++, an enhanced vision backbone designed to improve the performance of Mamba-based models, particularly with high-resolution inputs. This new architecture leverages the geometric …
-
Canonical knowledge distillation proves effective for semantic segmentation
A new research paper demonstrates that standard knowledge distillation techniques are surprisingly effective for semantic segmentation tasks. The study found that when accounting for computational budget, canonical logi…
-
New DGM-Net model offers efficient semantic segmentation with geometric guidance
Researchers have developed DGM-Net, an efficient architecture for semantic segmentation that bypasses the need for large models and high computational budgets. The network utilizes a novel Directional Geometric Mamba (G…