滑动
发表于 2025-3-25 06:17:03
Prototype Softmax Cross Entropy: A New Perspective on Softmax Cross Entropy focus on the loss function for the feature encoder. We show that Softmax Cross Entropy (SCE) can be interpreted as a special kind of loss function in contrastive learning with prototypes. This insight provides a completely new perspective on cross entropy, allowing the derivation of a new generaliz
强行引入
发表于 2025-3-25 11:06:44
http://reply.papertrans.cn/47/4614/461346/461346_22.png
Invigorate
发表于 2025-3-25 14:50:20
Synthesizing Hard Training Data from Latent Hierarchical Representationsto classify. This is used for data from an automatic visual defect inspection system, specifically images of vials with and without chipped glass. The hard samples were found by training ConvNeXt classifiers and using the confidences of the classifiers on the training dataset. VQ-VAE2 was used to ob
利用
发表于 2025-3-25 19:36:57
Rigidity Preserving Image Transformations and Equivariance in Perspectiveurns out that the only rigidity preserving image transformations are homographies corresponding to rotating the camera. In particular, 2D translations of pinhole images are not rigidity preserving. Hence, when using CNNs for 3D inference tasks, it can be beneficial to modify the inductive bias from
飞镖
发表于 2025-3-25 22:18:58
Tangent Phylogenetic PCAations are not independent, due to shared evolutionary history. The method works on Euclidean data, but in evolutionary biology there is a need for applying it to data on manifolds, particularly shapes. We provide a generalization of p-PCA to data lying on Riemannian manifolds, called .. Tangent p-P
溺爱
发表于 2025-3-26 03:14:01
Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular SpacesEuclidean or angular spaces. Euclidean distances between sample vectors are used during classification for the methods maximizing the margin in Euclidean spaces whereas the Cosine similarity distance is used during the testing stage for the methods maximizing margin in the angular spaces. This paper
Conspiracy
发表于 2025-3-26 06:15:16
http://reply.papertrans.cn/47/4614/461346/461346_27.png
护航舰
发表于 2025-3-26 09:22:55
http://reply.papertrans.cn/47/4614/461346/461346_28.png
决定性
发表于 2025-3-26 16:20:37
From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learningnal neural networks (CNNs) can automatically learn powerful task-aware features that are more discriminative and of higher representational capacity. To some extent, such hand-crafted features can be safely ignored when designing deep computer vision models. Nevertheless, due to LBP’s preferable pro
abracadabra
发表于 2025-3-26 18:43:20
http://reply.papertrans.cn/47/4614/461346/461346_30.png