Intermediate, Wholistic Shape Representation in Object Recognition: A Pre-Attentive Stage of Processing?

Evidence is presented for intermediate, wholistic visual representations of objects and non-objects that are computed online and independent of visual attention. Short-term visual priming was examined between visually similar shapes, with targets either falling at the (valid) location cued by primes or at another (invalid) location. Object decision latencies were facilitated when the overall shapes of the stimuli were similar irrespective of whether the location of the prime was valid or invalid, with the effects being equally large for object and non-object targets. In addition, the effects were based on the overall outlines of the stimuli and low spatial frequency components, not on local parts. In conclusion, wholistic shape representations based on outline form, are rapidly computed online during object recognition. Moreover, activation of common wholistic shape representations prime the processing of subsequent objects and non-objects irrespective of whether they appear at attended or unattended locations. Rapid derivation of wholistic form provides a key intermediate stage of object recognition.

Large-scale Image Classification with Explainable deep learning scheme

For the uncertainty and complexity in object decision making and the differences of decision makers ' reliabilities, an object decision making method based on deep learning theory is proposed. However, traditional deep learning approaches optimize the parameters in an "end-to-end" mode by annotating large amounts of data to propagate the errors backwards. The learning method could be considered to be as a "black box", which is weak in explainability. Explainability refers to an algorithm that gives a clear summary of a particular task and connects it to defined principles or principles in the human world. This paper proposes an explainable attention model consisting of channel attention module and spatial attention module. The proposed module derives attention graphs from channel dimension and spatial dimension respectively, then the input features are selectively learned according to the importance of the features. For different channels, the higher the weight, the higher the correlation which required more attention. The main function of spatial attention is to capture the most informative part in the local feature graph, which is a supplement to channel attention. We evaluate our proposed module based on the ImageNet-1K and Cifar-100 respectively. Experimental results show that our algorithm is superior in both accuracy and robustness compared with the state of the arts.

Highway Disaster Alignment Decision-making Model Under the Fragile Environment Condition in Mountain Area

Highway disaster alignment is a complex multi-object decision-making problem especially under frail environment conditions such as in mountainous areas. In addition, these objects do not have public characteristics. This paper established the multi-object functional decision making model from the topographic, geologic environmental aspect that may grow and become the cause of all kinds of highway disasters. Using the multi-object decision making theory, this model considered the multi-object forthe highway alignment from the qualitative and quantitative aspect, which has an important academic significance and applied value. In the end of this paper, an example of the analysis is given which indicated the model and its effectivness.

Refitting Sites Selection of Ocean Trawler Based on Fuzzy Matter-Element Model and Information Entropy Theory

Refitting sites selection of ocean trawler in wartime, is affected by a variety of technical factors and other factors such as organization, planning, management, and so on. The index system is given by detailed analysis of the influence factors. A fuzzy matter-element model is built up in view of the fuzziness and incompatibility of the indexes, combining quantitative analysis with qualitative analysis, with quantifying the qualitative indexes by linguistic variables and fuzzy numbers. The information entropy theory is used to calculate the value of index weights, to reduce the subjective randomness. The multi-objective selection problem is transformed into the single-object decision by Euclid approach degree. The example shows that the method is very practical and the result is objective.