Search Results for author:
Found 5 papers, 2 papers with code
Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
The Detection Transformer (DETR) has emerged as a pivotal role in object detection tasks, setting new performance benchmarks due to its end-to-end design and scalability.
Ranked #1 on
Oriented Object Detection
on DOTA 2.0
Deep Closed-Form Subspace Clustering
We propose Deep Closed-Form Subspace Clustering (DCFSC), a new embarrassingly simple model for subspace clustering with learning non-linear mapping.
Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions.
Rectified Gradient: Layer-wise Thresholding for Sharp and Coherent Attribution Maps
In this paper, we identify the cause of noisy saliency maps.
Noise-adding Methods of Saliency Map as Series of Higher Order Partial Derivative
SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input.
