20 results for “depth separation”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper provides the first algorithmic separation between constant-depth and logarithmic-depth networks, identifying a class of Boolean functions that logarithmic-depth networks can learn efficient…
This paper establishes all-depths depth separation for ReLU networks on {0,1}^n.
The paper introduces a Mixture-Density Representation (MDA) to model depth ambiguity, effectively eliminating 'flying-point' artifacts at object boundaries by allowing pixels to predict multiple possi…
This paper identifies scattering network architectures that maximize separation capacity for data with low intrinsic dimension by characterizing and bounding the separation capacity of general feature…
Jiangwei Ren, Xingyu Jiang, Zijie Song, Wei Xu +3 more
This paper proposes Wat3R, a cross-domain semi-supervised learning framework for adapting 3D reconstruction models from air to underwater scenes using unlabeled real underwater video footage and a tea…
A multi-stage framework is proposed for spatial semantic segmentation of sound scenes, achieving improved audio separation performance.
This paper explores how different components of the Transformer feedforward block architecture impact rank preservation across depth during initialization.
Vincent-Daniel Yun, Youngrae Kim, Woosang Lim, YoungJin Heo +2 more
The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…
Replacing global self-attention in stereo transformers with a data-independent Walsh-Hadamard token mixer reduces compute and latency by a factor of 2.46 and 2.65 respectively.
The paper introduces ZipDepth, a compact monocular depth network that achieves high zero-shot accuracy with low computational demands by combining an efficient encoder-decoder and large-scale knowledg…
A new deep learning method, Mamba Transformer, is proposed for accurate single-shot 3D reconstruction from a single high frequency fringe image.
Pengfei Wang, Shihao Wang, Liyi Chen, Zhiyuan Ma +2 more
This paper introduces DepthMaster, a unified metric depth estimation framework that achieves state-of-the-art performance on diverse datasets.
This paper studies the planar analog of the necklace splitting problem and presents algorithms to minimize the number of lines needed to divide colored points among agents.
A new framework for accurately estimating volume and surface area from multi-view images with low computational cost.